def extract_ivector(seq_file, file_list, gmm_file, model_file, preproc_file, output_path, qy_only, **kwargs): set_float_cpu('float32') sr_args = SR.filter_eval_args(**kwargs) if preproc_file is not None: preproc = TransformList.load(preproc_file) else: preproc = None gmm = DiagGMM.load_from_kaldi(gmm_file) sr = SR(seq_file, file_list, batch_size=1, shuffle_seqs=False, preproc=preproc, **sr_args) t1 = time.time() # if qy_only: # model = TVAEY.load(model_file) # else: model = TVAEYZ.load(model_file) model.build(max_seq_length=sr.max_batch_seq_length) y = np.zeros((sr.num_seqs, model.y_dim), dtype=float_keras()) xx = np.zeros((1, sr.max_batch_seq_length, model.x_dim), dtype=float_keras()) rr = np.zeros((1, sr.max_batch_seq_length, model.r_dim), dtype=float_keras()) keys = [] for i in xrange(sr.num_seqs): ti1 = time.time() x, key = sr.read_next_seq() ti2 = time.time() r = gmm.compute_z(x) ti3 = time.time() logging.info('Extracting i-vector %d/%d for %s, num_frames: %d' % (i, sr.num_seqs, key, x.shape[0])) keys.append(key) xx[:,:,:] = 0 rr[:,:,:] = 0 xx[0,:x.shape[0]] = x rr[0,:x.shape[0]] = r y[i] = model.compute_qy_x([xx, rr], batch_size=1)[0] ti4 = time.time() logging.info('Elapsed time i-vector %d/%d for %s, total: %.2f read: %.2f, gmm: %.2f, vae: %.2f' % (i, sr.num_seqs, key, ti4-ti1, ti2-ti1, ti3-ti2, ti4-ti3)) logging.info('Extract elapsed time: %.2f' % (time.time() - t1)) hw = HypDataWriter(output_path) hw.write(keys, '', y)
def extract_ivector(seq_file, file_list, model_file, preproc_file, output_path, qy_only, **kwargs): set_float_cpu('float32') sr_args = SR.filter_eval_args(**kwargs) if preproc_file is not None: preproc = TransformList.load(preproc_file) else: preproc = None sr = SR(seq_file, file_list, batch_size=1, shuffle_seqs=False, preproc=preproc, **sr_args) t1 = time.time() if qy_only: model = TVAEY.load(model_file) else: model = TVAEYZ.load(model_file) model.build(max_seq_length=sr.max_batch_seq_length) logging.info(time.time() - t1) logging.info(model.y_dim) y = np.zeros((sr.num_seqs, model.y_dim), dtype=float_keras()) xx = np.zeros((1, sr.max_batch_seq_length, model.x_dim), dtype=float_keras()) keys = [] for i in xrange(sr.num_seqs): x, key = sr.read_next_seq() logging.info('Extracting i-vector %d/%d for %s\n' % (i, sr.num_seqs, key)) keys.append(key) xx[:, :, :] = 0 xx[0, :x.shape[0]] = x y[i] = model.compute_qy_x(xx, batch_size=1)[0] logging.info('Extract elapsed time: %.2f' % (time.time() - t1)) hw = HypDataWriter(output_path) hw.write(keys, '', y)
def eval_elbo(seq_file, file_list, model_file, preproc_file, output_file, ubm_type, **kwargs): sr_args = SR.filter_eval_args(**kwargs) if preproc_file is not None: preproc = TransformList.load(preproc_file) else: preproc = None sr = SR(seq_file, file_list, batch_size=1, shuffle_seqs=False, preproc=preproc, **sr_args) t1 = time.time() if ubm_type == 'diag-gmm': model = DiagGMM.load(model_file) else: model = DiagGMM.load_from_kaldi(model_file) model.initialize() elbo = np.zeros((sr.num_seqs, ), dtype=float_cpu()) num_frames = np.zeros((sr.num_seqs, ), dtype=int) keys = [] for i in xrange(sr.num_seqs): x, key = sr.read_next_seq() keys.append(key) elbo[i] = model.elbo(x) num_frames[i] = x.shape[0] num_total_frames = np.sum(num_frames) total_elbo = np.sum(elbo) total_elbo_norm = total_elbo / num_total_frames logging.info('Extract elapsed time: %.2f' % (time.time() - t1)) s = 'Total ELBO: %f\nELBO_NORM %f' % (total_elbo, total_elbo_norm) logging.info(s) with open(output_file, 'w') as f: f.write(s)
def compute_gmm_post(seq_file, file_list, model_file, preproc_file, output_path, num_comp, **kwargs): sr_args = SR.filter_eval_args(**kwargs) if preproc_file is not None: preproc = TransformList.load(preproc_file) else: preproc = None gmm = DiagGMM.load_from_kaldi(model_file) sr = SR(seq_file, file_list, batch_size=1, shuffle_seqs=False, preproc=preproc, **sr_args) t1 = time.time() logging.info(time.time() - t1) index = np.zeros((sr.num_seqs, num_comp), dtype=int) hw = HypDataWriter(output_path) for i in xrange(sr.num_seqs): x, key = sr.read_next_seq() logging.info('Extracting i-vector %d/%d for %s, num_frames: %d' % (i, sr.num_seqs, key, x.shape[0])) r = gmm.compute_z(x) r_s, index = to_sparse(r, num_comp) if i == 0: r2 = to_dense(r_s, index, r.shape[1]) logging.degug(np.sort(r[0, :])[-12:]) logging.degug(np.sort(r2[0, :])[-12:]) logging.degug(np.argsort(r[0, :])[-12:]) logging.degug(np.argsort(r2[0, :])[-12:]) hw.write([key], '.r', [r_s]) hw.write([key], '.index', [index]) logging.info('Extract elapsed time: %.2f' % (time.time() - t1))
def extract_ivector(seq_file, file_list, gmm_file, model_file, preproc_file, output_path, qy_only, **kwargs): set_float_cpu('float32') sr_args = SR.filter_eval_args(**kwargs) if preproc_file is not None: preproc = TransformList.load(preproc_file) else: preproc = None gmm = DiagGMM.load_from_kaldi(gmm_file) sr = SR(seq_file, file_list, batch_size=1, shuffle_seqs=False, preproc=preproc, **sr_args) t1 = time.time() # if qy_only: # model = TVAEY.load(model_file) # else: model = TVAEYZ.load(model_file) #model.build(max_seq_length=sr.max_batch_seq_length) #model.build(max_seq_length=1) model.x_dim = 60 model.r_dim = 2048 model.y_dim = 400 y = np.zeros((sr.num_seqs, model.y_dim), dtype=float_keras()) xx = np.zeros((1, sr.max_batch_seq_length, model.x_dim), dtype=float_keras()) rr = np.zeros((1, sr.max_batch_seq_length, model.r_dim), dtype=float_keras()) keys = [] xp = Input(shape=( sr.max_batch_seq_length, model.x_dim, )) rp = Input(shape=( sr.max_batch_seq_length, model.r_dim, )) qy_param = model.qy_net([xp, rp]) qy_net = Model([xp, rp], qy_param) for i in xrange(sr.num_seqs): ti1 = time.time() x, key = sr.read_next_seq() ti2 = time.time() r = gmm.compute_z(x) ti3 = time.time() logging.info('Extracting i-vector %d/%d for %s, num_frames: %d' % (i, sr.num_seqs, key, x.shape[0])) keys.append(key) # xp = Input(shape=(x.shape[0], model.x_dim,)) # rp = Input(shape=(x.shape[0], model.r_dim,)) # qy_param = model.qy_net([xp, rp]) ti5 = time.time() xx[:, :, :] = 0 rr[:, :, :] = 0 xx[0, :x.shape[0]] = x rr[0, :x.shape[0]] = r # x = np.expand_dims(x, axis=0) # r = np.expand_dims(r, axis=0) # qy_net = Model([xp, rp], qy_param) y[i] = qy_net.predict([xx, rr], batch_size=1)[0] # del qy_net # y[i] = model.compute_qy_x2([x, r], batch_size=1)[0] #for i in xrange(10): #gc.collect() ti4 = time.time() logging.info( 'Elapsed time i-vector %d/%d for %s, total: %.2f read: %.2f, gmm: %.2f, vae: %.2f qy: %.2f' % (i, sr.num_seqs, key, ti4 - ti1, ti2 - ti1, ti3 - ti2, ti4 - ti5, ti5 - ti3)) # print('Elapsed time i-vector %d/%d for %s, total: %.2f read: %.2f, gmm: %.2f, vae: %.2f' % # (i, sr.num_seqs, key, ti4-ti1, ti2-ti1, ti3-ti2, ti4-ti3)) logging.info('Extract elapsed time: %.2f' % (time.time() - t1)) hw = HypDataWriter(output_path) hw.write(keys, '', y)
def extract_embed(seq_file, file_list, model_file, preproc_file, output_path, max_length, layer_names, **kwargs): set_float_cpu('float32') sr_args = SR.filter_eval_args(**kwargs) if preproc_file is not None: preproc = TransformList.load(preproc_file) else: preproc = None sr = SR(seq_file, file_list, batch_size=1, shuffle_seqs=False, preproc=preproc, **sr_args) t1 = time.time() model = SeqEmbed.load(model_file) model.build() print(layer_names) model.build_embed(layer_names) y_dim = model.embed_dim max_length = np.minimum(sr.max_batch_seq_length, max_length) y = np.zeros((sr.num_seqs, y_dim), dtype=float_keras()) xx = np.zeros((1, max_length, model.x_dim), dtype=float_keras()) keys = [] for i in xrange(sr.num_seqs): ti1 = time.time() x, key = sr.read_next_seq() ti2 = time.time() print('Extracting embeddings %d/%d for %s, num_frames: %d' % (i, sr.num_seqs, key, x.shape[0])) keys.append(key) xx[:, :, :] = 0 if x.shape[0] <= max_length: xx[0, :x.shape[0]] = x y[i] = model.predict_embed(xx, batch_size=1) else: num_chunks = int(np.ceil(float(x.shape[0]) / max_length)) chunk_size = int(np.ceil(float(x.shape[0]) / num_chunks)) for j in xrange(num_chunks - 1): start = j * chunk_size xx[0, :chunk_size] = x[start:start + chunk_size] y[i] += model.predict_embed(xx, batch_size=1).ravel() xx[0, :chunk_size] = x[-chunk_size:] y[i] += model.predict_embed(xx, batch_size=1).ravel() y[i] /= num_chunks ti4 = time.time() print( 'Elapsed time embeddings %d/%d for %s, total: %.2f read: %.2f, vae: %.2f' % (i, sr.num_seqs, key, ti4 - ti1, ti2 - ti1, ti4 - ti2)) print('Extract elapsed time: %.2f' % (time.time() - t1)) hw = HypDataWriter(output_path) hw.write(keys, '', y)
def extract_ivector(seq_file, file_list, gmm_file, model_file, preproc_file, output_path, qy_only, max_length, **kwargs): set_float_cpu('float32') sr_args = SR.filter_eval_args(**kwargs) if preproc_file is not None: preproc = TransformList.load(preproc_file) else: preproc = None gmm = DiagGMM.load_from_kaldi(gmm_file) sr = SR(seq_file, file_list, batch_size=1, shuffle_seqs=False, preproc=preproc, **sr_args) t1 = time.time() # if qy_only: # model = TVAEY.load(model_file) # else: model = TVAEYZ.load(model_file) #model.build(max_seq_length=sr.max_batch_seq_length) model.build(max_seq_length=1) max_length = np.minimum(sr.max_batch_seq_length, max_length) y = np.zeros((sr.num_seqs, model.y_dim), dtype=float_keras()) xx = np.zeros((1, max_length, model.x_dim), dtype=float_keras()) rr = np.zeros((1, max_length, model.r_dim), dtype=float_keras()) keys = [] xp = Input(shape=( max_length, model.x_dim, )) rp = Input(shape=( max_length, model.r_dim, )) qy_param = model.qy_net([xp, rp]) qy_net = Model([xp, rp], qy_param) for i in xrange(sr.num_seqs): ti1 = time.time() x, key = sr.read_next_seq() ti2 = time.time() r = gmm.compute_z(x) ti3 = time.time() logging.info('Extracting i-vector %d/%d for %s, num_frames: %d' % (i, sr.num_seqs, key, x.shape[0])) keys.append(key) xx[:, :, :] = 0 rr[:, :, :] = 0 if x.shape[0] <= max_length: xx[0, :x.shape[0]] = x rr[0, :x.shape[0]] = r y[i] = qy_net.predict([xx, rr], batch_size=1)[0] else: num_batches = int(np.ceil(x.shape[0] / max_length)) for j in xrange(num_batches - 1): start = j * max_length xx[0] = x[start:start + max_length] rr[0] = r[start:start + max_length] y[i] += qy_net.predict([xx, rr], batch_size=1)[0].ravel() xx[0] = x[-max_length:] rr[0] = r[-max_length:] y[i] += qy_net.predict([xx, rr], batch_size=1)[0].ravel() y[i] /= num_batches ti4 = time.time() logging.info( 'Elapsed time i-vector %d/%d for %s, total: %.2f read: %.2f, gmm: %.2f, vae: %.2f' % (i, sr.num_seqs, key, ti4 - ti1, ti2 - ti1, ti3 - ti2, ti4 - ti3)) logging.info('Extract elapsed time: %.2f' % (time.time() - t1)) hw = HypDataWriter(output_path) hw.write(keys, '', y)